An Efficient Hardwired Realization of Embedded Neural Controller on System-On-Programmable-Chip (SOPC)
|
|
- Shonda Robertson
- 6 years ago
- Views:
Transcription
1 An Efficient Hardwired Realization of Embedded Neural Controller on System-On-Programmable-Chip (SOPC) Karan Goel, Uday Arun, A. K. Sinha ABES Engineering College, Department of Computer Science & Engineering, Ghaziabad Membership, IEEE Circuit and System Society and ACM Embedded System Computing Society Membership, IEEE Computer Society Abstract In this paper, an efficient hardwired realization of Embedded Neural Controller (ENC) on Field Programmable Gate Array (FPGA/SOPC) is presented. This system architecture is described using Very High Speed Integrated Circuits Hardware Description Language (VHDL) and implemented on Xilinx FPGA/SOPC chip. A design is verified on a Xilinx FPGA/SOPC demo board. This paper discusses the issues involved in the implementation of a multi-input neuron with nonlinear activation function using FPGA/SOPC. The issues are parallel/sequential implementation of neurons, data representation and precision for the inputs, weights & activation function and the use of hybrid method (PLAN with RALUT approximation) for the approximation of a nonlinear, continuous, monotonically increasing, differentiable activation function. It is shown that fully parallel implementation of neurons is not feasible in hardware rather an alternative method called MAC circuit is used to overcome this problem. Moreover, fixed point (FXP) representation is proved to be better than floating point (FLP) representation. Finally, hardware realization of activation function is presented. The results are analysed in terms of low values of average error & maximum error, maximum working frequency, high speed of execution, low power consumption, less delay, less area, higher accuracy, low cost and usage percentage of chip resources such as number of slices (each slice is a logic unit which includes two 4-input look-up tables (LUT) & two flip-flops), number of Input/output blocks (IOB) & number of block RAMs. Here, the multiplier has a parallel, non-pipelined and combinational structure. Keywords: ANN, FPGA/SOPC, sigmoid activation function, tangent hyperbolic activation function, PlAN approximation, LUT approximation, RALUT approximation, hybrid approximation method. Introduction Artificial neural networks (ANNs) have been used in many fields such as solving pattern classification & recognition problems, signal processing, control system etc. Although, neural networks have been implemented mostly in software, hardware versions are gaining importance. Software versions have the advantage of being easy to implement, but with poor performance. Hardware versions are generally more difficult and time consuming to implement, but with better performance than software versions. Hardware version takes the advantage of neural network s inherent parallelism. Neural networks can be implemented using analog or digital systems. The analog ones are more precise but difficult to implement and have problem with weight storage. The digital implementation is more popular as it has the advantage of higher accuracy, better repeatability, lower noise sensitivity, better testability, higher flexibility, compatibility with other types of processors & has no problem with weight storage. The digital NN hardware implementation are further classified as DSP Embedded Development board, Microprocessor/Microcontroller based, ASICbased, VLSI-based, FPGA- based implementations. Digital Signal Processor (DSP) and microprocessor based implementation is sequential and hence does not preserve the parallel architecture of the neurons in a layer. Application Specific Integrated Circuit (ASIC) & Very Large Scale Integration (VLSI) based implementation do not offer re-configurability by the user, run only specific algorithms, expensive, time consuming to develop such chip and limitation on the size of the network. 276
2 FPGA is a suitable hardware for neural network implementation as it preserves the parallel architecture of the neurons in a layer and offer flexibility in reconfiguration and maintains high gate density which is needed to utilize the parallel computation in an ANN. Parallelism, modularity and dynamic adaptation are three computational characteristics typically associated with ANNs. Therefore, FPGA/SOPC based implementation is best suited to implement ANNs. FPGA/SOPC are a family of programmable device based on an array of configurable logic blocks (CLBs) which gives a great flexibility in prototyping, designing and development of complex hardware real time systems. When implementing ANN on FPGA/SOPC, certain measures are to be taken to minimize the hardware. These measures are the data representation and the number of bits (precision) of inputs, weights and the activation function. 1. Generic Architecture of Multilayer Neural Network (MLP) The Generic architecture of multilayer neural network shown in figure 1 consists of a layer of input nodes called input layer, one or more hidden layer(s) consisting of hidden nodes and one output layer consisting of output nodes NN Implementation with only One Input for the Weights Figure 2. NN implementation with only one input for the weights 2. Mathematical Model of a Single Artificial Neuron The common mathematical model of a single artificial neuron is shown as The neuron output can be written as: Input layer Hidden layer Output layer Where Figure 1. Generic architecture of MLP x1, x2 & x3 are the inputs. HN1 to HN6 are the hidden nodes that constitutes a hidden layer Y1, Y2, Y3 are the outputs of the network. Where p j is the input value and w j is the corresponding weight value, a is the output of the neuron and the f(.) is a nonlinear activation function. 3. Data Precision & Representation Before beginning a hardware implementation of an ANN, an arithmetic representation (floating point or fixed point) and the number of bits (precision) must be considered for the inputs, weights and activation function, which may range from 16 bit, 32 bit or 64 bit floating-point format (FLP) or fixed point format (FXP). Increasing the precision of the design elements significantly increases the resources used. 277
3 FLP format is area hungry with improved precision whereas FXP format needs minimal resources at the expense of precision. The minimum allowable precision and minimum allowable range is to be decided to conserve silicon area and power without affecting the performance of ANN. Precision of fixed point data is independent of the number but dependent on the position of the radix point. Antony W.Savich et al. [9] had shown that the resource requirement of networks implemented with FXP arithmetic is appreciably two times lesser than the FLP arithmetic with similar precision and range. Also FXP computation produces better convergence in lesser clock cycles. For a normalized input and output in the range of [0,1] to realize the log-sigmoid activation function, Holt and Bakes [10] showed that 16-bit FXP (1-3-12) representation was the minimum allowable precision. Ligon III et al. [11] exhibited the density advantage of 32-bit FXP computation over FLP computation for Xilinx FPGA/SOPC Analogy of Fixed Point Format The Fixed point format is defined as follows: [s] a.b Where the optional s denotes a sign bit with 0 for positive and 1 for negative numbers, a is the number of integer bits and b is the number of fractional bits. To represent negative numbers, two s complement notation is used. The examples in Table 1 clarify the notation. If the sign bit is used, the minimum x min and maximum x max numbers in a.b notation are x min = 2 -a x max = 2 a - 2 -b If the sign bit is not used, the minimum x min and maximum x max numbers in a.b notation are x min = 0 x max = 2 a - 2 -b 4. Implementation of Fully Parallel Neural Network A fully parallel network is fast but inflexible. In a fully parallel network, the number of multipliers per neuron must be equal to the number of connection to this neuron. Since all of the products must be summed, the number of full adders equals to the number of connections to the previous layer minus one. In architecture, the output neuron must have 5 multipliers and 4 Full-Adders, while each hidden neuron must have 3 multipliers and 2 adders. So, different neuron architectures have to be designed for each layer. A second drawback of a fully parallel network is gate resource usage because multipliers are costly hardware. Krips et. Al. [1] proposed such architecture. 278
4 5. Design and Modelling of Multiply and Accumulate (MAC) Circuit of a Neuron In this work, we chose multiply and accumulate structure for neurons. In this structure, there is one multiplier and one accumulator per neuron. The inputs from previous layer neurons enter the neuron serially and are multiplied with their corresponding weights. Every neuron has its own weight storage ROM. Multiplied values are summed in an accumulator. The processes are synchronized to clock (global) signal. The number of clock cycles for a neuron to finish its work is equals to the number of connections from the previous layer. The accumulator has a load signal, so that the bias values are loaded to all neurons at start-up. This neuron architecture is shown in figure 3. In this design, the neuron architecture is fixed throughout the network and is not dependent on the number of connection. coming from the previous layer is fed successively at each clock cycle. All of the neurons in the layer operate parallel. They take an input from their common input line, multiply it with the corresponding weight from their weight ROM and accumulate the product. If the previous layer has 3 neurons, present layer take and processes these inputs in 3 clock cycles. After these 3 clock cycles, every neuron in the layer has its net values ready. Then the layer starts to transfer these values to its output one by one for the next layer to take them successively by enabling corresponding neuron s three-state output. Since, only one neuron s output have to be present at the layer s output at a time, instead of implementing an activation function for each neuron, it is convenient to implement one activation function for each layer. The block diagram of a layer architecture including 3 neurons is shown in figure 4. Figure 3. Block diagram of a single neuron The precision of the weights and input values are both 8 bits. The multiplier is an 8-bit by 8-bit multiplier, which results in a 16-bit product, and the accumulator is 16-bits wide. The accumulator has also an enable signal, which enables the accumulating function and an out_enable signal for its three state outputs. Here the multiplier has a parallel, non-pipelined, combinational structure, generated by Xilinx Logicore Multiplier Generator V 5.0[4]. 6. Analysis & Synthesis of Layered Architecture of Multi-Neurons In our design, an ANN layer has one input which is connected to all neurons in this layer. But previous layer may have several outputs depending on the number of neurons it has. Each input to the layer Figure 4. Block diagram of a layer consisting of 3 neurons 7. Design, Modelling, Synthesis of Neural Network Architecture The control signals in the system are generated by a state machine. This state machine is responsible of controlling all of the operations in the network. First it activates the load signals of the neurons and 279
5 the neurons load their bias values. Then hidden layer is enabled for 3 clock cycles, and then the output layer consisting of a single neuron is enabled for 5 clock cycles. Out_enable signals are also activated by this state machine. The state machine generates weight ROM addresses in a priory determined sequence so that the same address lines can be used by all of the neurons in the system. Input RAM also uses this address line. Once the input RAM is loaded by input values using the switches on the board, the propagation phase starts and the output of the network is displayed. The block diagram of the network is shown in figure 5. The resource usage of the selected network architecture is shown in table 2. and is shown by figure 6. Figure 5. Block diagram of the complete neural network 8. Hardware Realization of Activation Function One of the important components in designing ANNs in hardware is the nonlinear activation function. The most common used function is sigmoid activation function and tangent hyperbolic activation function. These activation functions is a monotonically increasing, continuous, differential and nonlinear exponential function that limits the output of a neuron within the certain range i.e. [0,1] & [-1, 1] respectively. These functions are reported to be a better activation function for ANN. It is defined as: Figure 6. Log-sigmoid and hyperbolic tangent AF Straightforward implementation of these functions in hardware is not practical due to their exponential nature. Several different approaches exist for the hardware approximation of activation function, including piecewise linear approximation, look-up tables (LUT), Range addressable look-up tables and Hybrid Methods [2],[3],[4],[5],[6],[7],[8]. The efficiency criteria for a successful approximation are the achieved accuracy, speed and area resources Analysis of Piece-wise Linear Approximation of a Nonlinear Function (PLAN) Piecewise linear (PWL) approximations uses a series of linear segments to approximate the activation function [2]. Piecewise linear approximation is a method to obtain low values for both maximum and average error with low computational complexity. The number and locations of these segments are chosen such that error, processing time and area utilization are minimized. The number of pieces required in the PWL approximation of the activation function depends upon the complexity of the problem to be solved [12]. Using power of two co-efficient to represent the slope of the linear segments allows right shift operations instead of multiplication [12] to reduce the hardware as multipliers are expensive hardware components in terms of area and delay. Piecewise linear approximations are slow, but consume less area. For hardware implementation, it is convenient that the number of data points be a power of two, we will assume that the interval I is divided into 2 k intervals: 280
6 [L, L + (U-L)/ 2 k ), [L + (U-L)/ 2 k, L + 2(U-L)/2 k )..., [L + 2 k-1 (U-L)/2 k ) Where U and L are the upper and lower limit of inputs applied to the activation function respectively. Then, given an argument x, the interval into which it falls can readily be located by using, as an address, the k most significant bits of the binary representation of x. A piecewise linear approximation of the hyperbolic tangent function with five segments is shown in figure 7. Figure 7. Piecewise linear approximation of Tanh(x) with five segments The representation of five segments is shown as: Mod n : Subtraction : Constant adder Simulated results of PWL based approach is shown in table Analysis of LUT Approximation With this approach, the function is approximated by a limited number of uniformly distributed points [5], [7]. This methods results in high performance design, however it will require a large amount of memory to store the look up table (LUT) in hardware. The look-up table s input space is designed so that it covers a range between -8 and +8. In our data representation, this range corresponds to s4.5 format ie.. 10 bits. So, a 1024*8 ROM is needed to implement the activation function s look-up table. The LUT design does not optimize well under FLP format and hence fixed point format is used. But still on-chip realization of log-sigmoid function increases the size of hardware considerably. To optimize the area to some extent, the inbuilt RAM available in FPGA/SOPC is used to realize LUT based activation function. It reduces area and improves speed. If the precision is to improve, then PWL approximation approach of activation function is to be utilized along with the look-up table (Hybrid Method). The look-up table approximation of the sigmoid function with sixteen points is shown in figure 9. The computational modules of the activation function is as shown in figure 8. Figure 9. LUT approximation of sigmoid function with sixteen points Figure 8. Computational modules of the activation function Individual sub blocks are realized using FXP formats. 8-n : Inverter module /n : constant bit shifts The log sigmoid activation function is realized by representing input x in 10 bits and output f(x) in 8 bits. 10-bit input x has the following FXP format to represent the address of the memory location and output f(x) is represented as 8-bit fractional part only, to indicate the respective content of memory location. The data precision of the above two approaches (PWL and LUT approximation) of AF 281
7 is shown in table 3. Simulated results of LUT based approach is shown in table 6. Comparison of Synthesis report for LUT and PWL approximation using Xilinx is shown in table 5. situations where the output remains constant over a range. Examples are the hyperbolic tangent and the sigmoid functions, where the output changes only slightly outside the range of (-2, 2). A RALUT approximation of the hyperbolic tangent function with seven points is shown in figure 10. The smallest possible value that can be represented as output is 2 -n, where n is the number of bits in the stream. This value should be treated as zero, since f(x)=0 when x=minus infinity, which may never occur. Hence an error 2 -n is introduced. Similarly the largest possible value of f(x) is 1-2 -n to limit the output to be within (0, 1). Therefore, the minimum value of AF, f(x1) = 1 / (1+e -x1 ) = 2 -n which decides the lower limit of input, x1 = -ln (2 n 1) Similarly, the maximum vale of AF, f(x2) = 1 / (1 + e-x2) = 1-2 -n which decides the upper limit of input, x2 = ln (2n - 1) Hence, the step size or increment of input is found to be X = ln [( n ) / ( n )] The minimum number of LUT values is given by min number = (x2-x1) / X min number for the x1 and x2 respectively is found to be 710 for 8-bit precision. Hence 1K RAM with 10-bit address lines is chosen that gives 1024 locations with step size X = For a 10 bit input x, the minimum value x1 = and the maximum value is x2 = The output RAM has 1K memory in which 710 locations are used leaving 374 locations unused. Wastage of memory is a draw back and the second method (PWL) overcomes it RALUT approximation It shares many aspects with the classic LUT with a few notable differences. In LUTs, every data point stored in the table corresponds to a unique address. In RALUTs, every data point corresponds to a range of addresses. This alternate addressing allows for a large reduction in data points in Figure 10. RALUT approximation of hyperbolic tangent function 8.4. Analysis of Hybrid Method Approximation Hybrid methods usually combine two or more of the previously mentioned methods to achieve better performance. This method makes use of piecewise linear approximation along with the use of RALUT [8]. It initially makes use of a piecewise linear approximation with five segments to approximate the activation function. Afterwards, the difference between the actual function s value and the approximated value will be adjusted to achieve a better approximation. The adjustment values are calculated offline and stored in a lookup table. These adjustments consists of subtracting the values stored in the lookup table from the initial piecewise linear approximation. This can be achieved with a simple combinational subtracter circuit. This method has two main advantages. First, all the five segments were chosen to avoid the use of a multiplier in the design. Second, the lookup table used in our design stores the difference between the piecewise linear approximation and the actual function. This greatly minimizes the range of the output variance, which reduces the size of the lookup table. To further optimize the design, RALUT was used instead of classic LUT. The block diagram of the hybrid system is shown in figure 11. Complexity comparison of different implementation is shown in table
8 Table 5. Comparison of Synthesis report for LUT and PWL approximation using Xilinx Figure 11. System block for a hybrid method 9. Experimental results Table 2. Resource usage of the network architecture Table 5. Simulated results of LUT based approach Table 3. Data precision of LUT and PWL Activation function Table 7. Complexity comparison of different approximation method of activation function in terms of area and delay Table 4. Simulated results of PWL based approach 10. Conclusion Table 5. Simulated results of LUT based approach This work has presented the analysis, modeling, synthesis, verification, prototyping and implementation of embedded neural controller for high intelligent control systems on embedded SOPC & SPARTAN6 FPGA device. The proposed network architecture is modular, being possible to easily increase or decrease the number of neurons as well as layers. SOPC can be used for portable, modular, and reconfigurable hardwired solutions 283
9 for neural networks, which have been mostly used to be realized on computers until now. With the internal layer parallelism we used, it takes lesser clock cycles for the applied network to calculate its output as compared to microprocessor based implementation. Because neural networks are inherently parallel structures, parallel architectures always result faster than serial ones. Moreover, hardware implementation of an activation function that is used to realize an ANN is tried in this work. A two-fold approach to minimize the hardware is proposed here, aiming at the SOPC realization. Firstly, FXP arithmetic is followed against FLP arithmetic to reduce area, by compromising slightly on accuracy. Secondly, PLAN approximation with five linear segments along with RALUT is proved to be hardware friendly. 11. Future work Future research work includes the analysis, modeling, synthesis, verification, prototyping and implementation of embedded neural controller for high intelligent control systems on embedded SOPC & SPARTAN6 FPGA device, analysis & synthesis of hybrid approximation of activation function, pipelined based hybrid multiplier and memory elements for embedded neural controller. 12. References 1. M. Krips, T. Lammert, and Anton Kummert, FPGA Implementation of a Neural Network for a Real-Time Hand Tracking System, Proceedings of the first IEEE International Workshop on Electronic Design, Test and Applications, K. Basterretxea and J.M. Tarela and I. Del Campo, Approximation of sigmoid function and the derivative for hardware implementation of artificial neurons, IEE Proceedings - Circuits, Devices and Systems, vol. 151, no. 1, pp , February K. Basterretxea and J.M. Tarela, Approximation of sigmoid function and the derivative for artificial neurons, advances in neural networks and applications, WSES Press, Athens, pp , M.T. Tommiska, Efficient digital implementation of the sigmoid function for reprogrammable logic, IEE Proceedings on Computers and Digital Techniques, vol. 150, no. 6, pp , Nov K. Leboeuf, A.H. Namin, R. Muscedere, H. Wu, and M. Ahmadi Efficient Hardware Implementation of the Hyperbolic Tangent Sigmoid Function, Third International Conference on Convergence and hybrid Information Technology, accepted, November H.K. Kwan, Simple sigmoid-like activation function suitable for digital hardware implementation Electronic Letters,vol. 28, no. 15, pp , July F. Piazza, A. Uncini, and M. Zenobi, Neural networks with digital LUT activation functions, Proceedings of 1993 International Joint Conference on Neural Networks, IJCNN, pp ,October A.H. Namin, K. Leboeuf, R. Muscedere, H. Wu, and M. Ahmadi, HighSpeed VLSI Implementation of the Hyperbolic Tangent Sigmoid Function, IEEE International Symposium on Circuits and Systems (ISCAS), accepted, May Antony W. Savich, Medhat Moussa, and Shawki Areibi, The Impact of Arithmetic Representation on Implementing MLP-BP on FPGAs: A Study, IEEE Trans. Neural Networks, vol.18, no.1, Jan J. Holt and T. Baker, Back propagation simulations using limited precision calculations, in Proc. Int. Joint Conf. Neural Netw. (IJCNN-91), Seattle, WA, Jul. 1991, vol. 2, pp W. Ligon, III, S. McMillan, G. Monn, K. Schoonover, F. Stivers, andk. Underwood, A re-evaluation of the practicality of floating point operations on FPGAs, in Proc. IEEE Symp. FPGAs Custom Comput. Mach., K. L. Pocek and J. Arnold, Eds., Los Alamitos, CA, 1998, pp
A Library of Parameterized Floating-point Modules and Their Use
A Library of Parameterized Floating-point Modules and Their Use Pavle Belanović and Miriam Leeser Department of Electrical and Computer Engineering Northeastern University Boston, MA, 02115, USA {pbelanov,mel}@ece.neu.edu
More informationDIGITAL IMPLEMENTATION OF THE SIGMOID FUNCTION FOR FPGA CIRCUITS
DIGITAL IMPLEMENTATION OF THE SIGMOID FUNCTION FOR FPGA CIRCUITS Alin TISAN, Stefan ONIGA, Daniel MIC, Attila BUCHMAN Electronic and Computer Department, North University of Baia Mare, Baia Mare, Romania
More informationJournal of Engineering Technology Volume 6, Special Issue on Technology Innovations and Applications Oct. 2017, PP
Oct. 07, PP. 00-05 Implementation of a digital neuron using system verilog Azhar Syed and Vilas H Gaidhane Department of Electrical and Electronics Engineering, BITS Pilani Dubai Campus, DIAC Dubai-345055,
More informationIMPROVEMENTS TO THE BACKPROPAGATION ALGORITHM
Annals of the University of Petroşani, Economics, 12(4), 2012, 185-192 185 IMPROVEMENTS TO THE BACKPROPAGATION ALGORITHM MIRCEA PETRINI * ABSTACT: This paper presents some simple techniques to improve
More informationImplementation of FPGA-Based General Purpose Artificial Neural Network
Implementation of FPGA-Based General Purpose Artificial Neural Network Chandrashekhar Kalbande & Anil Bavaskar Dept of Electronics Engineering, Priyadarshini College of Nagpur, Maharashtra India E-mail
More informationISSN (Online), Volume 1, Special Issue 2(ICITET 15), March 2015 International Journal of Innovative Trends and Emerging Technologies
VLSI IMPLEMENTATION OF HIGH PERFORMANCE DISTRIBUTED ARITHMETIC (DA) BASED ADAPTIVE FILTER WITH FAST CONVERGENCE FACTOR G. PARTHIBAN 1, P.SATHIYA 2 PG Student, VLSI Design, Department of ECE, Surya Group
More informationFast Evaluation of the Square Root and Other Nonlinear Functions in FPGA
Edith Cowan University Research Online ECU Publications Pre. 20 2008 Fast Evaluation of the Square Root and Other Nonlinear Functions in FPGA Stefan Lachowicz Edith Cowan University Hans-Joerg Pfleiderer
More informationINTRODUCTION TO FPGA ARCHITECTURE
3/3/25 INTRODUCTION TO FPGA ARCHITECTURE DIGITAL LOGIC DESIGN (BASIC TECHNIQUES) a b a y 2input Black Box y b Functional Schematic a b y a b y a b y 2 Truth Table (AND) Truth Table (OR) Truth Table (XOR)
More informationFPGA Implementation of Multiplier for Floating- Point Numbers Based on IEEE Standard
FPGA Implementation of Multiplier for Floating- Point Numbers Based on IEEE 754-2008 Standard M. Shyamsi, M. I. Ibrahimy, S. M. A. Motakabber and M. R. Ahsan Dept. of Electrical and Computer Engineering
More informationIEEE-754 compliant Algorithms for Fast Multiplication of Double Precision Floating Point Numbers
International Journal of Research in Computer Science ISSN 2249-8257 Volume 1 Issue 1 (2011) pp. 1-7 White Globe Publications www.ijorcs.org IEEE-754 compliant Algorithms for Fast Multiplication of Double
More informationDesign and Implementation of VLSI 8 Bit Systolic Array Multiplier
Design and Implementation of VLSI 8 Bit Systolic Array Multiplier Khumanthem Devjit Singh, K. Jyothi MTech student (VLSI & ES), GIET, Rajahmundry, AP, India Associate Professor, Dept. of ECE, GIET, Rajahmundry,
More informationA SIMULINK-TO-FPGA MULTI-RATE HIERARCHICAL FIR FILTER DESIGN
A SIMULINK-TO-FPGA MULTI-RATE HIERARCHICAL FIR FILTER DESIGN Xiaoying Li 1 Fuming Sun 2 Enhua Wu 1, 3 1 University of Macau, Macao, China 2 University of Science and Technology Beijing, Beijing, China
More informationFast evaluation of nonlinear functions using FPGAs
Adv. Radio Sci., 6, 233 237, 2008 Author(s) 2008. This work is distributed under the Creative Commons Attribution 3.0 License. Advances in Radio Science Fast evaluation of nonlinear functions using FPGAs
More informationImplementation of CORDIC Algorithms in FPGA
Summer Project Report Implementation of CORDIC Algorithms in FPGA Sidharth Thomas Suyash Mahar under the guidance of Dr. Bishnu Prasad Das May 2017 Department of Electronics and Communication Engineering
More informationHIGH-PERFORMANCE RECONFIGURABLE FIR FILTER USING PIPELINE TECHNIQUE
HIGH-PERFORMANCE RECONFIGURABLE FIR FILTER USING PIPELINE TECHNIQUE Anni Benitta.M #1 and Felcy Jeba Malar.M *2 1# Centre for excellence in VLSI Design, ECE, KCG College of Technology, Chennai, Tamilnadu
More informationField Programmable Gate Array (FPGA)
Field Programmable Gate Array (FPGA) Lecturer: Krébesz, Tamas 1 FPGA in general Reprogrammable Si chip Invented in 1985 by Ross Freeman (Xilinx inc.) Combines the advantages of ASIC and uc-based systems
More informationEvaluation of High Speed Hardware Multipliers - Fixed Point and Floating point
International Journal of Electrical and Computer Engineering (IJECE) Vol. 3, No. 6, December 2013, pp. 805~814 ISSN: 2088-8708 805 Evaluation of High Speed Hardware Multipliers - Fixed Point and Floating
More informationAn Optimized Montgomery Modular Multiplication Algorithm for Cryptography
118 IJCSNS International Journal of Computer Science and Network Security, VOL.13 No.1, January 2013 An Optimized Montgomery Modular Multiplication Algorithm for Cryptography G.Narmadha 1 Asst.Prof /ECE,
More informationInternational Journal of Advanced Research in Computer Science and Software Engineering
ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: Configuring Floating Point Multiplier on Spartan 2E Hardware
More informationPipelined Quadratic Equation based Novel Multiplication Method for Cryptographic Applications
, Vol 7(4S), 34 39, April 204 ISSN (Print): 0974-6846 ISSN (Online) : 0974-5645 Pipelined Quadratic Equation based Novel Multiplication Method for Cryptographic Applications B. Vignesh *, K. P. Sridhar
More informationSynthesis of VHDL Code for FPGA Design Flow Using Xilinx PlanAhead Tool
Synthesis of VHDL Code for FPGA Design Flow Using Xilinx PlanAhead Tool Md. Abdul Latif Sarker, Moon Ho Lee Division of Electronics & Information Engineering Chonbuk National University 664-14 1GA Dekjin-Dong
More informationFPGA Matrix Multiplier
FPGA Matrix Multiplier In Hwan Baek Henri Samueli School of Engineering and Applied Science University of California Los Angeles Los Angeles, California Email: chris.inhwan.baek@gmail.com David Boeck Henri
More informationImplementation of 14 bits floating point numbers of calculating units for neural network hardware development
International Conference on Recent Trends in Physics 206 (ICRTP206) Journal of Physics: Conference Series 755 (206) 000 doi:0.088/742-6596/755//000 Implementation of 4 bits floating numbers of calculating
More informationPerformance Analysis of CORDIC Architectures Targeted by FPGA Devices
International OPEN ACCESS Journal Of Modern Engineering Research (IJMER) Performance Analysis of CORDIC Architectures Targeted by FPGA Devices Guddeti Nagarjuna Reddy 1, R.Jayalakshmi 2, Dr.K.Umapathy
More informationVHDL IMPLEMENTATION OF FLOATING POINT MULTIPLIER USING VEDIC MATHEMATICS
VHDL IMPLEMENTATION OF FLOATING POINT MULTIPLIER USING VEDIC MATHEMATICS I.V.VAIBHAV 1, K.V.SAICHARAN 1, B.SRAVANTHI 1, D.SRINIVASULU 2 1 Students of Department of ECE,SACET, Chirala, AP, India 2 Associate
More informationAn Efficient Constant Multiplier Architecture Based On Vertical- Horizontal Binary Common Sub-Expression Elimination Algorithm
Volume-6, Issue-6, November-December 2016 International Journal of Engineering and Management Research Page Number: 229-234 An Efficient Constant Multiplier Architecture Based On Vertical- Horizontal Binary
More informationIMPLEMENTATION OF DOUBLE PRECISION FLOATING POINT RADIX-2 FFT USING VHDL
IMPLEMENTATION OF DOUBLE PRECISION FLOATING POINT RADIX-2 FFT USING VHDL Tharanidevi.B 1, Jayaprakash.R 2 Assistant Professor, Dept. of ECE, Bharathiyar Institute of Engineering for Woman, Salem, TamilNadu,
More informationMCM Based FIR Filter Architecture for High Performance
ISSN No: 2454-9614 MCM Based FIR Filter Architecture for High Performance R.Gopalana, A.Parameswari * Department Of Electronics and Communication Engineering, Velalar College of Engineering and Technology,
More informationAn Efficient Implementation of Multi Layer Perceptron Neural Network for Signal Processing
An Efficient Implementation of Multi Layer Perceptron Neural Network for Signal Processing A.THILAGAVATHY 1, M.E Vlsi Desgin(Pg Scholar), Srinivasan Engineering College, Perambalur-621 212, Tamilnadu,
More informationFPGA Implementation of a Nonlinear Two Dimensional Fuzzy Filter
Justin G. R. Delva, Ali M. Reza, and Robert D. Turney + + CORE Solutions Group, Xilinx San Jose, CA 9514-3450, USA Department of Electrical Engineering and Computer Science, UWM Milwaukee, Wisconsin 5301-0784,
More informationDigital Electronics 27. Digital System Design using PLDs
1 Module -27 Digital System Design 1. Introduction 2. Digital System Design 2.1 Standard (Fixed function) ICs based approach 2.2 Programmable ICs based approach 3. Comparison of Digital System Design approaches
More informationDESIGN AND PERFORMANCE ANALYSIS OF CARRY SELECT ADDER
DESIGN AND PERFORMANCE ANALYSIS OF CARRY SELECT ADDER Bhuvaneswaran.M 1, Elamathi.K 2 Assistant Professor, Muthayammal Engineering college, Rasipuram, Tamil Nadu, India 1 Assistant Professor, Muthayammal
More informationUniversity, Patiala, Punjab, India 1 2
1102 Design and Implementation of Efficient Adder based Floating Point Multiplier LOKESH BHARDWAJ 1, SAKSHI BAJAJ 2 1 Student, M.tech, VLSI, 2 Assistant Professor,Electronics and Communication Engineering
More informationBinary Adders. Ripple-Carry Adder
Ripple-Carry Adder Binary Adders x n y n x y x y c n FA c n - c 2 FA c FA c s n MSB position Longest delay (Critical-path delay): d c(n) = n d carry = 2n gate delays d s(n-) = (n-) d carry +d sum = 2n
More informationDesign of Convolution Encoder and Reconfigurable Viterbi Decoder
RESEARCH INVENTY: International Journal of Engineering and Science ISSN: 2278-4721, Vol. 1, Issue 3 (Sept 2012), PP 15-21 www.researchinventy.com Design of Convolution Encoder and Reconfigurable Viterbi
More informationDeveloping a Data Driven System for Computational Neuroscience
Developing a Data Driven System for Computational Neuroscience Ross Snider and Yongming Zhu Montana State University, Bozeman MT 59717, USA Abstract. A data driven system implies the need to integrate
More informationFPGA architecture and design technology
CE 435 Embedded Systems Spring 2017 FPGA architecture and design technology Nikos Bellas Computer and Communications Engineering Department University of Thessaly 1 FPGA fabric A generic island-style FPGA
More informationTSEA44 - Design for FPGAs
2015-11-24 Now for something else... Adapting designs to FPGAs Why? Clock frequency Area Power Target FPGA architecture: Xilinx FPGAs with 4 input LUTs (such as Virtex-II) Determining the maximum frequency
More informationPROJECT REPORT IMPLEMENTATION OF LOGARITHM COMPUTATION DEVICE AS PART OF VLSI TOOLS COURSE
PROJECT REPORT ON IMPLEMENTATION OF LOGARITHM COMPUTATION DEVICE AS PART OF VLSI TOOLS COURSE Project Guide Prof Ravindra Jayanti By Mukund UG3 (ECE) 200630022 Introduction The project was implemented
More informationFPGA Implementation of Multiplierless 2D DWT Architecture for Image Compression
FPGA Implementation of Multiplierless 2D DWT Architecture for Image Compression Divakara.S.S, Research Scholar, J.S.S. Research Foundation, Mysore Cyril Prasanna Raj P Dean(R&D), MSEC, Bangalore Thejas
More informationImplementation and Analysis of an Error Detection and Correction System on FPGA
Implementation and Analysis of an Error Detection and Correction System on FPGA Constantin Anton, Laurenţiu Mihai Ionescu, Ion Tutănescu, Alin Mazăre, Gheorghe Şerban University of Piteşti, Romania Abstract
More informationFused Floating Point Arithmetic Unit for Radix 2 FFT Implementation
IOSR Journal of VLSI and Signal Processing (IOSR-JVSP) Volume 6, Issue 2, Ver. I (Mar. -Apr. 2016), PP 58-65 e-issn: 2319 4200, p-issn No. : 2319 4197 www.iosrjournals.org Fused Floating Point Arithmetic
More informationPERFORMANCE ANALYSIS OF HIGH EFFICIENCY LOW DENSITY PARITY-CHECK CODE DECODER FOR LOW POWER APPLICATIONS
American Journal of Applied Sciences 11 (4): 558-563, 2014 ISSN: 1546-9239 2014 Science Publication doi:10.3844/ajassp.2014.558.563 Published Online 11 (4) 2014 (http://www.thescipub.com/ajas.toc) PERFORMANCE
More informationLECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS
LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Neural Networks Classifier Introduction INPUT: classification data, i.e. it contains an classification (class) attribute. WE also say that the class
More informationON THE IMPLEMENTATION OF DIFFERENT HYPERBOLIC TANGENT SOLUTIONS IN FPGA. Darío Baptista and Fernando Morgado-Dias
ON THE IMPLEMENTATION OF DIFFERENT HYPERBOLIC TANGENT SOLUTIONS IN FPGA Darío Baptista and Fernando Morgado-Dias Madeira Interactive Technologies Institute and Centro de Competências de Ciências Exactas
More informationLow Power and Memory Efficient FFT Architecture Using Modified CORDIC Algorithm
Low Power and Memory Efficient FFT Architecture Using Modified CORDIC Algorithm 1 A.Malashri, 2 C.Paramasivam 1 PG Student, Department of Electronics and Communication K S Rangasamy College Of Technology,
More informationDESIGN AND IMPLEMENTATION OF VLSI SYSTOLIC ARRAY MULTIPLIER FOR DSP APPLICATIONS
International Journal of Computing Academic Research (IJCAR) ISSN 2305-9184 Volume 2, Number 4 (August 2013), pp. 140-146 MEACSE Publications http://www.meacse.org/ijcar DESIGN AND IMPLEMENTATION OF VLSI
More informationInternational Journal of Advanced Research in Computer Science and Software Engineering
ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: Implementation of Floating Point Multiplier on Reconfigurable
More informationFPGA IMPLEMENTATION OF FLOATING POINT ADDER AND MULTIPLIER UNDER ROUND TO NEAREST
FPGA IMPLEMENTATION OF FLOATING POINT ADDER AND MULTIPLIER UNDER ROUND TO NEAREST SAKTHIVEL Assistant Professor, Department of ECE, Coimbatore Institute of Engineering and Technology Abstract- FPGA is
More informationIMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL NETWORK (ANN) FOR FULL ADDER. Research Scholar, IIT Kharagpur.
Journal of Analysis and Computation (JAC) (An International Peer Reviewed Journal), www.ijaconline.com, ISSN 0973-2861 Volume XI, Issue I, Jan- December 2018 IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL
More informationDesign and Implementation of CVNS Based Low Power 64-Bit Adder
Design and Implementation of CVNS Based Low Power 64-Bit Adder Ch.Vijay Kumar Department of ECE Embedded Systems & VLSI Design Vishakhapatnam, India Sri.Sagara Pandu Department of ECE Embedded Systems
More informationNew Computational Modeling for Solving Higher Order ODE based on FPGA
New Computational Modeling for Solving Higher Order ODE based on FPGA Alireza Fasih 1, Tuan Do Trong 2, Jean Chamberlain Chedjou 3, Kyandoghere Kyamakya 4 1, 3, 4 Alpen-Adria University of Klagenfurt Austria
More informationTopics. Midterm Finish Chapter 7
Lecture 9 Topics Midterm Finish Chapter 7 ROM (review) Memory device in which permanent binary information is stored. Example: 32 x 8 ROM Five input lines (2 5 = 32) 32 outputs, each representing a memory
More informationAnalysis of Different Multiplication Algorithms & FPGA Implementation
IOSR Journal of VLSI and Signal Processing (IOSR-JVSP) Volume 4, Issue 2, Ver. I (Mar-Apr. 2014), PP 29-35 e-issn: 2319 4200, p-issn No. : 2319 4197 Analysis of Different Multiplication Algorithms & FPGA
More informationFPGAs: FAST TRACK TO DSP
FPGAs: FAST TRACK TO DSP Revised February 2009 ABSRACT: Given the prevalence of digital signal processing in a variety of industry segments, several implementation solutions are available depending on
More informationA Low Power Asynchronous FPGA with Autonomous Fine Grain Power Gating and LEDR Encoding
A Low Power Asynchronous FPGA with Autonomous Fine Grain Power Gating and LEDR Encoding N.Rajagopala krishnan, k.sivasuparamanyan, G.Ramadoss Abstract Field Programmable Gate Arrays (FPGAs) are widely
More informationDesigning and Characterization of koggestone, Sparse Kogge stone, Spanning tree and Brentkung Adders
Vol. 3, Issue. 4, July-august. 2013 pp-2266-2270 ISSN: 2249-6645 Designing and Characterization of koggestone, Sparse Kogge stone, Spanning tree and Brentkung Adders V.Krishna Kumari (1), Y.Sri Chakrapani
More informationAdaptive FIR Filter Using Distributed Airthmetic for Area Efficient Design
International Journal of Scientific and Research Publications, Volume 5, Issue 1, January 2015 1 Adaptive FIR Filter Using Distributed Airthmetic for Area Efficient Design Manish Kumar *, Dr. R.Ramesh
More informationCOPY RIGHT. To Secure Your Paper As Per UGC Guidelines We Are Providing A Electronic Bar Code
COPY RIGHT 2018IJIEMR.Personal use of this material is permitted. Permission from IJIEMR must be obtained for all other uses, in any current or future media, including reprinting/republishing this material
More informationA Ripple Carry Adder based Low Power Architecture of LMS Adaptive Filter
A Ripple Carry Adder based Low Power Architecture of LMS Adaptive Filter A.S. Sneka Priyaa PG Scholar Government College of Technology Coimbatore ABSTRACT The Least Mean Square Adaptive Filter is frequently
More informationSimulation & Synthesis of FPGA Based & Resource Efficient Matrix Coprocessor Architecture
Simulation & Synthesis of FPGA Based & Resource Efficient Matrix Coprocessor Architecture Jai Prakash Mishra 1, Mukesh Maheshwari 2 1 M.Tech Scholar, Electronics & Communication Engineering, JNU Jaipur,
More informationEECS150 - Digital Design Lecture 6 - Field Programmable Gate Arrays (FPGAs)
EECS150 - Digital Design Lecture 6 - Field Programmable Gate Arrays (FPGAs) September 12, 2002 John Wawrzynek Fall 2002 EECS150 - Lec06-FPGA Page 1 Outline What are FPGAs? Why use FPGAs (a short history
More informationHigh Speed Special Function Unit for Graphics Processing Unit
High Speed Special Function Unit for Graphics Processing Unit Abd-Elrahman G. Qoutb 1, Abdullah M. El-Gunidy 1, Mohammed F. Tolba 1, and Magdy A. El-Moursy 2 1 Electrical Engineering Department, Fayoum
More informationPrachi Sharma 1, Rama Laxmi 2, Arun Kumar Mishra 3 1 Student, 2,3 Assistant Professor, EC Department, Bhabha College of Engineering
A Review: Design of 16 bit Arithmetic and Logical unit using Vivado 14.7 and Implementation on Basys 3 FPGA Board Prachi Sharma 1, Rama Laxmi 2, Arun Kumar Mishra 3 1 Student, 2,3 Assistant Professor,
More informationOutline. EECS150 - Digital Design Lecture 6 - Field Programmable Gate Arrays (FPGAs) FPGA Overview. Why FPGAs?
EECS150 - Digital Design Lecture 6 - Field Programmable Gate Arrays (FPGAs) September 12, 2002 John Wawrzynek Outline What are FPGAs? Why use FPGAs (a short history lesson). FPGA variations Internal logic
More informationEfficient Conversion From Binary to Multi-Digit Multi-Dimensional Logarithmic Number Systems using Arrays of Range Addressable Look- Up Tables
Efficient Conversion From Binary to Multi-Digit Multi-Dimensional Logarithmic Number Systems using Arrays of Range Addressable Look- Up Tables R. Muscedere 1, V.S. Dimitrov 2, G.A. Jullien 2, and W.C.
More informationDesign and Optimized Implementation of Six-Operand Single- Precision Floating-Point Addition
2011 International Conference on Advancements in Information Technology With workshop of ICBMG 2011 IPCSIT vol.20 (2011) (2011) IACSIT Press, Singapore Design and Optimized Implementation of Six-Operand
More informationCompact Clock Skew Scheme for FPGA based Wave- Pipelined Circuits
International Journal of Communication Engineering and Technology. ISSN 2277-3150 Volume 3, Number 1 (2013), pp. 13-22 Research India Publications http://www.ripublication.com Compact Clock Skew Scheme
More informationECE 341 Midterm Exam
ECE 341 Midterm Exam Time allowed: 90 minutes Total Points: 75 Points Scored: Name: Problem No. 1 (10 points) For each of the following statements, indicate whether the statement is TRUE or FALSE: (a)
More informationFPGA. Logic Block. Plessey FPGA: basic building block here is 2-input NAND gate which is connected to each other to implement desired function.
FPGA Logic block of an FPGA can be configured in such a way that it can provide functionality as simple as that of transistor or as complex as that of a microprocessor. It can used to implement different
More informationFPGA Implementation and Validation of the Asynchronous Array of simple Processors
FPGA Implementation and Validation of the Asynchronous Array of simple Processors Jeremy W. Webb VLSI Computation Laboratory Department of ECE University of California, Davis One Shields Avenue Davis,
More informationHigh Level Abstractions for Implementation of Software Radios
High Level Abstractions for Implementation of Software Radios J. B. Evans, Ed Komp, S. G. Mathen, and G. Minden Information and Telecommunication Technology Center University of Kansas, Lawrence, KS 66044-7541
More informationRUN-TIME RECONFIGURABLE IMPLEMENTATION OF DSP ALGORITHMS USING DISTRIBUTED ARITHMETIC. Zoltan Baruch
RUN-TIME RECONFIGURABLE IMPLEMENTATION OF DSP ALGORITHMS USING DISTRIBUTED ARITHMETIC Zoltan Baruch Computer Science Department, Technical University of Cluj-Napoca, 26-28, Bariţiu St., 3400 Cluj-Napoca,
More informationOverview. CSE372 Digital Systems Organization and Design Lab. Hardware CAD. Two Types of Chips
Overview CSE372 Digital Systems Organization and Design Lab Prof. Milo Martin Unit 5: Hardware Synthesis CAD (Computer Aided Design) Use computers to design computers Virtuous cycle Architectural-level,
More informationPINE TRAINING ACADEMY
PINE TRAINING ACADEMY Course Module A d d r e s s D - 5 5 7, G o v i n d p u r a m, G h a z i a b a d, U. P., 2 0 1 0 1 3, I n d i a Digital Logic System Design using Gates/Verilog or VHDL and Implementation
More informationARITHMETIC operations based on residue number systems
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II: EXPRESS BRIEFS, VOL. 53, NO. 2, FEBRUARY 2006 133 Improved Memoryless RNS Forward Converter Based on the Periodicity of Residues A. B. Premkumar, Senior Member,
More informationOPTIMIZATION OF AREA COMPLEXITY AND DELAY USING PRE-ENCODED NR4SD MULTIPLIER.
OPTIMIZATION OF AREA COMPLEXITY AND DELAY USING PRE-ENCODED NR4SD MULTIPLIER. A.Anusha 1 R.Basavaraju 2 anusha201093@gmail.com 1 basava430@gmail.com 2 1 PG Scholar, VLSI, Bharath Institute of Engineering
More informationImplementation and Impact of LNS MAC Units in Digital Filter Application
Implementation and Impact of LNS MAC Units in Digital Filter Application Hari Krishna Raja.V.S *, Christina Jesintha.R * and Harish.I * * Department of Electronics and Communication Engineering, Sri Shakthi
More informationParallelized Radix-4 Scalable Montgomery Multipliers
Parallelized Radix-4 Scalable Montgomery Multipliers Nathaniel Pinckney and David Money Harris 1 1 Harvey Mudd College, 301 Platt. Blvd., Claremont, CA, USA e-mail: npinckney@hmc.edu ABSTRACT This paper
More informationVLSI Design Of a Novel Pre Encoding Multiplier Using DADDA Multiplier. Guntur(Dt),Pin:522017
VLSI Design Of a Novel Pre Encoding Multiplier Using DADDA Multiplier 1 Katakam Hemalatha,(M.Tech),Email Id: hema.spark2011@gmail.com 2 Kundurthi Ravi Kumar, M.Tech,Email Id: kundurthi.ravikumar@gmail.com
More informationFPGA for Complex System Implementation. National Chiao Tung University Chun-Jen Tsai 04/14/2011
FPGA for Complex System Implementation National Chiao Tung University Chun-Jen Tsai 04/14/2011 About FPGA FPGA was invented by Ross Freeman in 1989 SRAM-based FPGA properties Standard parts Allowing multi-level
More informationProgrammable Logic Devices FPGA Architectures II CMPE 415. Overview This set of notes introduces many of the features available in the FPGAs of today.
Overview This set of notes introduces many of the features available in the FPGAs of today. The majority use SRAM based configuration cells, which allows fast reconfiguation. Allows new design ideas to
More informationFPGA Implementation of a High Speed Multistage Pipelined Adder Based CORDIC Structure for Large Operand Word Lengths
International Journal of Computer Science and Telecommunications [Volume 3, Issue 5, May 2012] 105 ISSN 2047-3338 FPGA Implementation of a High Speed Multistage Pipelined Adder Based CORDIC Structure for
More informationDESIGN TRADEOFF ANALYSIS OF FLOATING-POINT. ADDER IN FPGAs
DESIGN TRADEOFF ANALYSIS OF FLOATING-POINT ADDER IN FPGAs A Thesis Submitted to the College of Graduate Studies and Research In Partial Fulfillment of the Requirements For the Degree of Master of Science
More informationARCHITECTURAL DESIGN OF 8 BIT FLOATING POINT MULTIPLICATION UNIT
ARCHITECTURAL DESIGN OF 8 BIT FLOATING POINT MULTIPLICATION UNIT Usha S. 1 and Vijaya Kumar V. 2 1 VLSI Design, Sathyabama University, Chennai, India 2 Department of Electronics and Communication Engineering,
More informationAn FPGA based Implementation of Floating-point Multiplier
An FPGA based Implementation of Floating-point Multiplier L. Rajesh, Prashant.V. Joshi and Dr.S.S. Manvi Abstract In this paper we describe the parameterization, implementation and evaluation of floating-point
More informationAn Efficient Implementation of Floating Point Multiplier
An Efficient Implementation of Floating Point Multiplier Mohamed Al-Ashrafy Mentor Graphics Mohamed_Samy@Mentor.com Ashraf Salem Mentor Graphics Ashraf_Salem@Mentor.com Wagdy Anis Communications and Electronics
More informationarxiv: v1 [cs.ne] 25 Sep 2016
Accurate and Efficient Hyperbolic Tangent Activation Function on FPGA using the DCT Interpolation Filter Ahmed M. Abdelsalam, J.M. Pierre Langlois and F. Cheriet Computer and Software Engineering Department
More informationWORD LEVEL FINITE FIELD MULTIPLIERS USING NORMAL BASIS
WORD LEVEL FINITE FIELD MULTIPLIERS USING NORMAL BASIS 1 B.SARGUNAM, 2 Dr.R.DHANASEKARAN 1 Assistant Professor, Department of ECE, Avinashilingam University, Coimbatore 2 Professor & Director-Research,
More informationImplementation of Floating Point Multiplier Using Dadda Algorithm
Implementation of Floating Point Multiplier Using Dadda Algorithm Abstract: Floating point multiplication is the most usefull in all the computation application like in Arithematic operation, DSP application.
More informationDesign and Implementation of Floating Point Multiplier for Better Timing Performance
Design and Implementation of Floating Point Multiplier for Better Timing Performance B.Sreenivasa Ganesh 1,J.E.N.Abhilash 2, G. Rajesh Kumar 3 SwarnandhraCollege of Engineering& Technology 1,2, Vishnu
More informationA Novel Efficient VLSI Architecture for IEEE 754 Floating point multiplier using Modified CSA
RESEARCH ARTICLE OPEN ACCESS A Novel Efficient VLSI Architecture for IEEE 754 Floating point multiplier using Nishi Pandey, Virendra Singh Sagar Institute of Research & Technology Bhopal Abstract Due to
More informationREALIZATION OF MULTIPLE- OPERAND ADDER-SUBTRACTOR BASED ON VEDIC MATHEMATICS
REALIZATION OF MULTIPLE- OPERAND ADDER-SUBTRACTOR BASED ON VEDIC MATHEMATICS NEETA PANDEY 1, RAJESHWARI PANDEY 2, SAMIKSHA AGARWAL 3, PRINCE KUMAR 4 Department of Electronics and Communication Engineering
More informationDigital Logic & Computer Design CS Professor Dan Moldovan Spring 2010
Digital Logic & Computer Design CS 434 Professor Dan Moldovan Spring 2 Copyright 27 Elsevier 5- Chapter 5 :: Digital Building Blocks Digital Design and Computer Architecture David Money Harris and Sarah
More informationAn Efficient Hardware Architecture for a Neural Network Activation Function Generator
An Efficient Hardware Architecture for a Neural Network Activation Function Generator Daniel Larkin, Andrew Kinane, Valentin Muresan, and Noel O Connor Centre for Digital Video Processing, Dublin City
More informationNEURON IMPLEMENTATION USING SYSTEM GENERATOR
NEURON IMPLEMENTATION USING SYSTEM GENERATOR Luis Aguiar,2, Leonardo Reis,2, Fernando Morgado Dias,2 Centro de Competências de Ciências Exactas e da Engenharia, Universidade da Madeira Campus da Penteada,
More informationVLSI Design and Implementation of High Speed and High Throughput DADDA Multiplier
VLSI Design and Implementation of High Speed and High Throughput DADDA Multiplier U.V.N.S.Suhitha Student Department of ECE, BVC College of Engineering, AP, India. Abstract: The ever growing need for improved
More informationHigh Speed Pipelined Architecture for Adaptive Median Filter
Abstract High Speed Pipelined Architecture for Adaptive Median Filter D.Dhanasekaran, and **Dr.K.Boopathy Bagan *Assistant Professor, SVCE, Pennalur,Sriperumbudur-602105. **Professor, Madras Institute
More informationSpiral 2-8. Cell Layout
2-8.1 Spiral 2-8 Cell Layout 2-8.2 Learning Outcomes I understand how a digital circuit is composed of layers of materials forming transistors and wires I understand how each layer is expressed as geometric
More informationNumeric Encodings Prof. James L. Frankel Harvard University
Numeric Encodings Prof. James L. Frankel Harvard University Version of 10:19 PM 12-Sep-2017 Copyright 2017, 2016 James L. Frankel. All rights reserved. Representation of Positive & Negative Integral and
More information